granite3.1-dense:2b

granite · 2.5B · Q4_K_M

Good

Mar 2, 2026 · Apple M4

neural-chat:7b

llama · 7B · Q4_0

Good

Mar 2, 2026 · Apple M4

Global Score

68 vs 67

Hardware Fit

100 vs 96

Quality Score

54 vs 55

Hardware

granite3.1-dense:2b neural-chat:7b

MachineMacBook AirMacBook Air

CPUApple M4Apple M4

Cores1010

RAM32 GB32 GB

GPUApple M4Apple M4

OSmacOS 26.3macOS 26.3

Archarm64arm64

Power Modebalancedbalanced

Performance

granite3.1-dense:2b neural-chat:7b

Tokens/sec54.622.5

TTFT121 ms242 ms

Load time0.4 s0.4 s

Memory usage5.6 GB4.5 GB

Memory %18%14%

HW Fit Score Breakdown

granite3.1-dense:2b

Speed

40/40

TTFT

30/30

Memory

30/30

neural-chat:7b

Speed

36/40

TTFT

30/30

Memory

30/30

Quality

granite3.1-dense:2b

Reasoning

8/20

Coding

9/20

Instruction

13/20

Structured

14/15

Math

3/15

Multilingual

7/10

Reasoning: Weak Coding: Weak Instruction Following: Adequate Structured Output: Strong Math: Poor Multilingual: Adequate

neural-chat:7b

Reasoning

7/20

Coding

9/20

Instruction

12/20

Structured

12/15

Math

7/15

Multilingual

8/10

Reasoning: Weak Coding: Weak Instruction Following: Adequate Structured Output: Strong Math: Weak Multilingual: Strong

View granite3.1-dense:2b details | View neural-chat:7b details

Run yours and compare

npx metrillm@latest bench

Requires Node 20+ and Ollama or LM Studio running